Privacy Policy

1. Information We Collect

GitHub Profile Data

When you sign in via GitHub OAuth, we receive your GitHub username, email address, and avatar URL. This data is used to create and identify your account.

API Usage Data

We collect aggregated usage metrics including API calls per day/month, endpoints used, and response latencies. This data is used to enforce tier limits and monitor service health.

Memory Data

Data stored by your AI agents through the Mnemora API (working state, semantic memories, episodic logs, procedural definitions) is your data. We store it to provide the Service and do not access, analyze, or use it for any other purpose.

Payment Information

Payment processing is handled by Creala. We do not store credit card numbers or payment credentials. We receive only transaction confirmation and subscription status from Creala.

2. How We Use Information

• Provide, maintain, and improve the Service
• Monitor usage to enforce tier limits and prevent abuse
• Send service-related communications (downtime notices, security alerts)
• Respond to support requests

We do NOT sell your data to third parties. We do NOT use your data for advertising.

3. Data Storage

All data is stored in AWS us-east-1 region using DynamoDB, Aurora PostgreSQL, and S3. All data is encrypted at rest (AES-256 for DynamoDB and S3, Postgres TDE for Aurora) and encrypted in transit via TLS. API keys are SHA-256 hashed before storage and are never stored in plaintext.

4. Data Retention

• Account data is retained while your account is active
• Memory data is permanently deleted upon account deletion
• Service logs are retained for 30 days and then automatically purged
• Aggregated, anonymized usage statistics may be retained indefinitely

5. Your Rights

• Access: You can access all your data through the Mnemora API at any time
• Delete: You can delete your data through the API or by contacting us at isaac@mnemora.dev
• Export: The API provides full access to all your stored data for export purposes
• Portability: All data formats are documented and use standard JSON

6. Third-Party Services

We use the following third-party services to operate Mnemora:

• AWS — Cloud infrastructure (DynamoDB, Aurora, S3, Lambda)
• Vercel — Dashboard hosting
• GitHub — Authentication via OAuth
• Creala — Payment processing
• Amazon Bedrock (Titan) — Embedding generation for semantic memory. Text is processed to generate vectors but is not stored by the embedding service.

7. Children's Privacy

Mnemora is not intended for use by individuals under the age of 13. We do not knowingly collect personal information from children. If we become aware that we have collected data from a child under 13, we will take steps to delete it promptly.

8. Changes to This Policy

We may update this Privacy Policy from time to time. Material changes will be communicated via the dashboard or email. The “Last updated” date at the top of this page reflects the most recent revision.

9. Contact

For questions about this Privacy Policy or to exercise your data rights, contact us at isaac@mnemora.dev.